Related papers: Modernizing SMT-Based Type Error Localization
The ability of transformers to perform precision tasks such as question answering, Natural Language Inference (NLI) or summarising, have enabled them to be ranked as one of the best paradigm to address Natural Language Processing (NLP)…
Gradual typing enables developers to annotate types of their own choosing, offering a flexible middle ground between no type annotations and a fully statically typed language. As more and more code bases get type-annotated, static type…
Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…
Localizing type errors is challenging in languages with global type inference, as the type checker must make assumptions about what the programmer intended to do. We introduce Nate, a data-driven approach to error localization based on…
Dynamic languages are praised for their flexibility and expressiveness, but static analysis often yields many false positives and verification is cumbersome for lack of structure. Hence, unit testing is the prevalent incomplete method for…
Large Language Models (LLMs) have made remarkable progress in mathematical reasoning, but still continue to struggle with high-precision tasks like numerical computation and formal symbolic manipulation. Integrating external tools has…
The program synthesis problem within the Inductive Logic Programming (ILP) community has typically been seen as untyped. We consider the benefits of user provided types on background knowledge. Building on the Meta-Interpretive Learning…
I/O efficiency is crucial to productivity in scientific computing, but the increasing complexity of the system and the applications makes it difficult for practitioners to understand and optimize I/O behavior at scale. Data-driven machine…
Online programming courses are becoming more and more popular, but they still have significant drawbacks when compared to the traditional education system, e.g., the lack of feedback. In this study, we apply machine learning methods to…
The complexity of software in embedded systems has increased significantly over the last years so that software verification now plays an important role in ensuring the overall product quality. In this context, SAT-based bounded model…
Technical Debt (TD) identification in software projects issues is crucial for maintaining code quality, reducing long-term maintenance costs, and improving overall project health. This study advances TD classification using…
Dynamic languages, such as Python and Javascript, trade static typing for developer flexibility and productivity. Lack of static typing can cause run-time exceptions and is a major factor for weak IDE support. To alleviate these issues, PEP…
Tool-integrated reasoning (TIR) enables LLM agents to solve tasks through planning, tool use, and iterative revision, but outcome-only reinforcement learning in this setting suffers from sparse, delayed rewards and weak step-level credit…
Researchers have recently designed a number of application-specific fault tolerance mechanisms that enable applications to either be naturally resilient to errors or include additional detection and correction steps that can bring the…
Environmental noise (e.g.heat, ionized particles, etc.) causes transient faults in hardware, which lead to corruption of stored values. Mission-critical devices require such faults to be mitigated by fault-tolerance --- a combination of…
Type inference is crucial for reusing online code snippets. Although snippets are prevalently shared on platforms like StackOverflow, they often lack essential type information, such as fully qualified names (FQNs). Recent studies have…
Tool-integrated reasoning (TIR) has become a key approach for improving large reasoning models (LRMs) on complex problems. Prior work has mainly studied when to invoke tools, while overlooking how tools are applied. We identify two common…
Is the Text to Motion model robust? Recent advancements in Text to Motion models primarily stem from more accurate predictions of specific actions. However, the text modality typically relies solely on pre-trained Contrastive Language-Image…
Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment methods offer a lightweight alternative, but have been explored mainly…
Modern Network Intrusion Detection Systems generate vast volumes of low-level alerts, yet these outputs remain semantically fragmented, requiring labor-intensive manual correlation with high-level adversarial behaviors. Existing solutions…